Tool Response Injection Detector

ModernBert fine-tuned over rgeada/tool_response_injections. Intended for use with NeMo Guardrails' HuggingFace Classifier rails, as a tool-response injection guardrail.

Scores:

  • Test F1-Score: 0.8464
  • Test Accuracy: 0.8466
Downloads last month
21
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for rgeada/tool-response-injection-detector

Finetuned
(1417)
this model

Dataset used to train rgeada/tool-response-injection-detector